Exploring the forecasting approach for road accidents: Analytical measures with hybrid machine learning

Urban traffic forecasting models generally follow either a Gaussian Mixture Model (GMM) or Support Vector Classifier (SVC) to estimate the features of potential road accidents. Although SVC can provide good performances with less data than GMM, it incurs higher computational cost. This paper proposes novel framework that combines descriptive strength high-performance classification capabilities Classifier. A new approach is presented uses mean vectors obtained from GMM model as input SVC. Experimental results show compares very favorably baseline statistical methods.